Improving Performance of Semi-Supervised Learning by Adversarial Attacks

08/08/2023
by   Dongyoon Yang, et al.
0

Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, three recent SSL algorithms with SCAR result in significantly improved image classification.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset